Penelope: Emotions in NLP

In this multidisciplinary project we bring together philosophy, psychology and NLP to explore emotion analysis and related tasks in NLP. So far, we conducted a survey of the field in recent years, focusing in particular in the types of frameworks used in NLP research. We also showed that Large Language Models (LLMs) show significant gender bias, not only ascribing different emotions to men and women given the same events but doing so in line with existing stereotypes: men are overwhelmingly angry and women, overwhelmingly sad.

Collaborators: